Triple
T24583164
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2013 Westgate shopping mall attack |
E608306
|
entity |
| Predicate | responseForce |
P151947
|
FINISHED |
| Object | Kenya Defence Forces |
—
|
NE NERFINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Kenya Defence Forces | Statement: [2013 Westgate shopping mall attack, responseForce, Kenya Defence Forces]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: responseForce Context triple: [2013 Westgate shopping mall attack, responseForce, Kenya Defence Forces]
-
A.
responseSetting
Indicates the contextual conditions or configuration under which a response is produced or intended to be used.
-
B.
responseFormula
Indicates that one entity’s reaction, reply, or outcome is expressed or encoded in a specific formula or structured representation.
-
C.
responseUnit
chosen
Indicates a unit or entity that provides or carries out a response in relation to another entity or event.
-
D.
responseTool
Indicates a tool, method, or mechanism used to produce, deliver, or manage a response in a given context.
-
E.
responseFrom
Indicates that one entity is the originator or source of a response directed to another entity or request.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69e2c4ce89248190ad99e18f0638dfbb |
completed | April 17, 2026, 11:39 p.m. |
| NER | Named-entity recognition | batch_69f2a984577881908c855f5e05756909 |
completed | April 30, 2026, 12:59 a.m. |
| PD | Predicate disambiguation | batch_69f2a6c1f07081908edf0b521767e79b |
completed | April 30, 2026, 12:48 a.m. |
Created at: April 18, 2026, 2:29 a.m.